© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13928
    Prev
    Next
    INDEX
    Explanations

    say pipe

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .URI
    -20.00
    稷
    -18.38
    建筑设计
    -18.38
    RSA
    -18.00
     Agenda
    -17.75
    EDIA
    -17.63
     JSONException
    -17.38
     Architect
    -17.25
    Construct
    -17.00
     Construct
    -16.88
    POSITIVE LOGITS
     pipe
    18.13
    pipe
    17.25
     pipes
    17.13
     Pipe
    16.25
    itty
    16.00
     PIPE
    15.38
     cracks
    15.13
    Pipe
    14.88
     chuck
    14.88
     Pipes
    14.63
    Activations Density 0.671%

    No Known Activations